Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating widespread international or national coverage

    oai_token-act-pair · gpt-3.5-turbo

    references to global locations and notable places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.78
    ierre
    -0.77
    xit
    -0.75
    nect
    -0.74
    aroo
    -0.72
    uci
    -0.72
    omas
    -0.69
    icho
    -0.68
    vg
    -0.68
    ulhu
    -0.67
    POSITIVE LOGITS
     rainbow
    0.86
     aisle
    0.82
     nodd
    0.79
     corners
    0.73
     fuss
    0.72
    igree
    0.71
     dozen
    0.71
     arena
    0.71
     imaginable
    0.68
     globe
    0.67
    Act Density 0.111%

    No Known Activations